CN116258674A - Method and device for evaluating quality of assembly of visual inspection system - Google Patents
Method and device for evaluating quality of assembly of visual inspection system Download PDFInfo
- Publication number
- CN116258674A CN116258674A CN202211708942.6A CN202211708942A CN116258674A CN 116258674 A CN116258674 A CN 116258674A CN 202211708942 A CN202211708942 A CN 202211708942A CN 116258674 A CN116258674 A CN 116258674A
- Authority
- CN
- China
- Prior art keywords
- target
- image
- quality
- adjustment
- detection system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The application discloses a method and a device for evaluating the quality of assembly and adjustment of a visual detection system, and belongs to the technical field of assembly and adjustment of visual systems. The method for evaluating the quality of the assembly quality of the visual detection system comprises the following steps: adjusting system parameters of the visual detection system to target parameters based on the imaging effect of the product image corresponding to the product to be detected, which is acquired by the visual detection system; under the target parameters, respectively acquiring a plurality of target images corresponding to the target targets acquired by the visual detection system under a plurality of different adjustment offsets; extracting image features corresponding to pits in a target image, and determining an association relationship between the image features and the adjustment offset; and carrying out quantization processing on the association relation, and determining a quantization relation among image information of the target image, the tuning quality of the visual detection system and the tuning offset. The method for evaluating the quality of the assembly quality of the visual inspection system improves the evaluation accuracy and precision and also improves the consistency of appearance defect imaging among a plurality of visual inspection systems.
Description
Technical Field
The application belongs to the technical field of visual system adjustment, and particularly relates to an adjustment quality evaluation method and device for a visual detection system.
Background
In the field of machine vision defect detection, a visual detection system is often used to collect a product image to detect defects on a product based on the product image, however, in the actual detection process, the appearance of defects in the product image is also affected by the adjustment of the visual detection system. In the related art, aiming at the installation and debugging of a series of large-scale visual detection system equipment, a designed tool is generally adopted, and a plurality of equipment are assembled and regulated to the same state as much as possible by using the tool.
Disclosure of Invention
The present application aims to solve at least one of the technical problems existing in the prior art. Therefore, the application provides a method and a device for evaluating the quality of assembly of a visual inspection system, which improve the consistency of appearance defect imaging among a plurality of visual inspection systems.
In a first aspect, the present application provides a method for evaluating a quality of a visual inspection system, the method comprising:
adjusting system parameters of the visual detection system to target parameters based on imaging effects of product images corresponding to products to be detected, which are acquired by the visual detection system, wherein the target parameters are used for enabling the imaging effects to reach a target range;
Under the target parameters, respectively acquiring a plurality of target images corresponding to a target acquired by the visual detection system under a plurality of different adjustment offsets, wherein the product to be detected and the target are positioned on the same imaging surface, and a plurality of pits with different sizes are arranged on the surface of the target;
extracting image features corresponding to the pits in the target image, and determining an association relationship between the image features and the adjustment offset;
carrying out quantization processing on the association relation, and determining a quantization relation among image information of the target image, the tuning quality of the visual detection system and the tuning offset; the image information includes gray information and defect morphology.
According to the method for evaluating the quality of the assembly and adjustment of the visual inspection system, a quantitative relation between the image quality, the quality of the assembly and adjustment of the visual inspection system and the assembly and adjustment deviation of the visual inspection system is established, so that the influence of subjective judgment on the quality of the assembly and adjustment is avoided, the accuracy and precision of evaluation are improved, the consistency of the appearance defect imaging of a single visual inspection system along with the change of time can be monitored, and the consistency of the appearance defect imaging among a plurality of visual inspection systems can be effectively improved; repeated debugging processes are avoided, and the debugging efficiency in the installation and debugging scene of a series of large-scale visual detection system equipment is remarkably improved.
According to one embodiment of the present application, the quantization processing for the association relationship, determining the quantization relationship among the image information of the target image, the tuning quality of the visual detection system, and the tuning offset, includes:
performing image processing on target images in the target images, and determining the average gray scale and pixel value standard deviation of the target images;
based on the average gray scale and the pixel value standard deviation, respectively determining a first dark pixel area and a second dark pixel area of an image feature corresponding to the pit in the target image;
determining a target quantization relation corresponding to the target image based on the first dark pixel area, the second dark pixel area, the emphasis factor and the adjustment quality;
the emphasis factor is used for representing the gray information and the emphasis degree of the defect morphology, and the target image is a target image acquired by the visual detection system under a target tone offset in the plurality of different tone offsets.
According to one embodiment of the present application, the determining, based on the first dark pixel area, the second dark pixel area, the emphasis factor, and the adjustment quality, the target quantization relation corresponding to the target image includes:
Based on the formula:
determining a target quantization relation corresponding to the target image, wherein Z is the adjustment quality of the visual detection system under the target adjustment offset; d is the first dark pixel area; l is the second dark pixel area; lambda is the emphasis factor;
is the average gray scale.
According to one embodiment of the present application, the determining, based on the average gray scale and the standard deviation of the pixel values, a first dark pixel area and a second dark pixel area of an image feature corresponding to the pit in the target image includes:
determining a first threshold based on a difference between the average gray scale and the standard deviation of the pixel values of the target multiple;
determining the first dark pixel area based on the first threshold, a height of the target image of interest, and a width of the target image of interest;
determining a second threshold based on a sum of the average gray scale and the standard deviation of the pixel values of the target multiples;
the second dark pixel area is determined based on the second threshold, the height of the target image of interest, and the width of the target image of interest.
According to one embodiment of the present application, the acquiring, respectively, a plurality of target images corresponding to a target of interest acquired by the visual inspection system under a plurality of different tuning offsets includes:
Acquiring a plurality of initial images corresponding to the target acquired by the visual detection system under a target tone offset in the plurality of different tone offsets;
preprocessing the plurality of initial images to obtain at least one target image acquired by a visual detection system under the target adjustment;
the plurality of target images are acquired based on the plurality of different tone offsets.
According to one embodiment of the present application, after the quantization processing is performed on the association relationship, and the image information of the target image, the tuning quality of the visual detection system, and the quantization relationship between the tuning offsets are determined, the method further includes:
based on the quantization relation, determining the actual adjustment quality corresponding to the visual detection system to be detected;
and adjusting the vision detection system to be detected based on the actual adjustment quality.
In a second aspect, the present application provides a device for evaluating the quality of a visual inspection system, the device comprising:
the first processing module is used for adjusting system parameters of the visual detection system to target parameters based on the imaging effect of the product image corresponding to the product to be detected, which is acquired by the visual detection system, wherein the target parameters are used for enabling the imaging effect to reach a target range;
The second processing module is used for respectively acquiring a plurality of target images corresponding to a target, acquired by the visual detection system under a plurality of different adjustment offsets, of the target under the target parameters, wherein the product to be detected and the target are positioned on the same imaging surface, and a plurality of pits with different sizes are arranged on the surface of the target;
the third processing module is used for extracting image features corresponding to the pits in the target image and determining the association relationship between the image features and the adjustment offset;
the fourth processing module is used for carrying out quantization processing on the association relation and determining an image information of the target image, the adjustment quality of the visual detection system and a quantization relation between the adjustment offsets; the image information includes gray information and defect morphology.
According to the visual inspection system assembling quality evaluation device, a quantitative relation between the image quality, the visual inspection system assembling quality and the visual inspection system assembling offset is established, so that the influence of subjective judgment on the assembling quality is avoided, the evaluation accuracy and precision are improved, the consistency of the appearance defect imaging of a single visual inspection system along with the change of time can be monitored, and the consistency of the appearance defect imaging among a plurality of visual inspection systems can be effectively improved; repeated debugging processes are avoided, and the debugging efficiency in the installation and debugging scene of a series of large-scale visual detection system equipment is remarkably improved.
In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the method for evaluating the quality of packaging of a visual inspection system according to the first aspect when the processor executes the computer program.
In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method for evaluating the quality of packaging of a visual inspection system as described in the first aspect above.
In a fifth aspect, the present application provides a chip, where the chip includes a processor and a communication interface, where the communication interface is coupled to the processor, and where the processor is configured to execute a program or instructions to implement the method for evaluating a thermal load of a visual inspection system according to the first aspect.
In a sixth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, implements the method for evaluating the quality of fit of a visual inspection system as described in the first aspect above.
The above technical solutions in the embodiments of the present application have at least one of the following technical effects:
By establishing quantitative relation among the image quality, the adjustment quality of the visual detection system and the adjustment offset of the visual system, the influence of subjective judgment on the adjustment quality is avoided, the accuracy and the precision of evaluation are improved, the consistency of the change of the appearance defect imaging of a single visual detection system along with time can be monitored, and the consistency of the appearance defect imaging among a plurality of visual detection systems can be effectively improved; repeated debugging processes are avoided, and the debugging efficiency in the installation and debugging scene of a series of large-scale visual detection system equipment is remarkably improved.
Furthermore, by setting the emphasis factors to establish quantitative relation between gray information, defect morphology, adjustment quality and adjustment offset based on the emphasis factors, the emphasis factors are conveniently adjusted to correspondingly adjust the quantitative relation based on the emphasis degree of the gray information and defect morphology, so that the adjustment quality can be more accurately judged, and the method has higher use flexibility and wider application scene.
Furthermore, the actual adjustment quality of the visual detection system is determined through a quantitative relation, so that a user can monitor the imaging state of a single device conveniently, discover the difference between the defect presentation state and the initial state in time, remind the user to calibrate or re-adjust the device, and realize the real-time dynamic monitoring of the defect presentation state in the use process.
Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, wherein:
FIG. 1 is a schematic flow chart of a method for evaluating the quality of a visual inspection system according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a method for evaluating the quality of a visual inspection system according to an embodiment of the present disclosure;
FIG. 3 is a second schematic diagram showing the effect of the method for evaluating the quality of the visual inspection system according to the embodiment of the present application;
FIG. 4 is a third schematic view showing the effect of the method for evaluating the quality of the visual inspection system according to the embodiment of the present application;
FIG. 5 is a diagram showing the effect of the method for evaluating the quality of the visual inspection system according to the embodiment of the present application;
FIG. 6 is a schematic diagram showing the effect of the method for evaluating the quality of the visual inspection system according to the embodiment of the present application;
FIG. 7 is a second schematic diagram of the method for evaluating the quality of the visual inspection system according to the embodiment of the present application;
FIG. 8 is a schematic structural view of a visual inspection system mounting quality evaluation device according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application are within the scope of the protection of the present application.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type and not limited to the number of objects, e.g., the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.
The method for evaluating the quality of the visual inspection system, the device for evaluating the quality of the visual inspection system, the electronic device and the readable storage medium according to the embodiments of the present application will be described in detail with reference to the accompanying drawings.
According to the method for evaluating the quality of the visual inspection system, the execution main body of the method for evaluating the quality of the visual inspection system can be a device for evaluating the quality of the visual inspection system, or can be a server, or can also be a user terminal, including but not limited to a mobile phone, a tablet personal computer, a computer and the like.
As shown in fig. 1, the method for evaluating the quality of the assembly of the visual inspection system includes: step 110, step 120, step 130 and step 140.
in this step, the imaging effect includes imaging brightness and the like.
The target parameter is used for enabling the brightness of the product image of the product to be detected to be in a target range.
As shown in fig. 2, the product to be measured is located on the same imaging plane as the target.
In the actual implementation process, the target and the product to be detected can be placed on the same imaging surface, parameters of the visual detection system are adjusted to target parameters under different adjustment offsets, so that the brightness of a product image of the product to be detected is adjusted to a target range, the gray level of the image can be kept within a reasonable range after on-site adjustment is simulated, and then the target image of the target and the product image of the product to be detected are acquired, as shown in fig. 3-5.
in this step, the target of interest is a user-defined target.
The surface of the target is provided with a plurality of pits with different sizes.
In the actual implementation process, the target may be a film target, as shown in fig. 7, the film target may be inserted from a middle position, and pits with different sizes are pressed out on the film target as defects by pressing the tooling.
The visual inspection system includes an image sensor and a light source, and the different adjustment offsets include, but are not limited to, an offset in the mounting angle of the image sensor, an offset in the mounting angle of the light source, and the like.
In the image acquisition process, the adjustment offset of the visual system is changed by placing the target under the visual field of the visual detection system, so as to acquire target images of the target under each adjustment offset.
In this step, the random deviation of the on-site tone is simulated by changing the tone offset.
In some embodiments, step 120 may include:
acquiring a plurality of initial images corresponding to a target acquired by a visual detection system under a target adjustment offset in a plurality of different adjustment offsets;
preprocessing a plurality of initial images to obtain at least one target image acquired by a visual detection system under target adjustment;
a plurality of target images are acquired based on a plurality of different tone offsets.
In this embodiment, the target tone offset is any of a plurality of different tone offsets.
The tone offsets corresponding to the plurality of initial images are the same, and the corresponding target targets are also the same.
After a plurality of initial images are acquired, the plurality of initial images can be preprocessed to remove images with larger errors, at least one initial image is acquired, and the initial image is taken as a target image, so that interference of random errors is avoided, and accuracy of a subsequent evaluation result is improved.
And then changing the adjustment offset, acquiring a plurality of initial images under each adjustment offset, and preprocessing to screen and obtain at least one target image under each adjustment offset.
For example, in the actual implementation process, the target and the product to be tested may be placed on the same imaging plane, and parameters of the visual detection system may be adjusted under different adjustment offsets, so as to adjust brightness of a product image of the product to be tested to a preset range, so that the gray scale of the image can be kept within a reasonable range after on-site adjustment is simulated, and then the target image of the target and the product image of the product to be tested are collected, as shown in fig. 3-5.
Fig. 3 (a) is a plurality of target images corresponding to a target with an adjustment offset of 0.0mm, and fig. 3 (b) is a plurality of product images corresponding to a product to be tested with an adjustment offset of 0.0 mm.
Fig. 4 (a) is a plurality of target images corresponding to a target with a tone shift of 0.5mm, and fig. 4 (b) is a plurality of product images corresponding to a product to be tested with a tone shift of 0.5 mm.
Fig. 5 (a) is a plurality of target images corresponding to a target at a set-up offset of 1.0mm, and fig. 5 (b) is a plurality of product images corresponding to a product to be tested at a set-up offset of 1.0 mm.
130, extracting image features corresponding to pits in a target image, and determining an association relationship between the image features and the tone offset;
in this step, the image features corresponding to the pits include an area, a gradation, a shadow range around the feature, and the like.
As shown in fig. 6, fig. 6 (a) is a target image corresponding to a target of interest at a pitch shift of 0mm, fig. 6 (b) is a target image corresponding to a target of interest at a pitch shift of 0.5mm, fig. 6 (c) is a target image corresponding to a target of interest at a pitch shift of 1mm, and fig. 6 (d) is a target image corresponding to a target of interest at a pitch shift of 1.5 mm.
The area of the black dot in the target image is used for reflecting the area of the pit defect, along with the increase of the tone offset, the shadow appears around the pit defect, and the defective pixel is divided into two parts of black and white, so that erroneous judgment is brought to the image algorithm processing.
With continued reference to fig. 6, as the pitch offset increases, the change of the pit in the target image also changes in a trending manner, and based on the trend of change between the two, the association relationship between the image feature and the pitch offset can be determined.
After the association relationship is obtained, the association relationship is further converted into a quantization relationship through step 140, so that the quantization evaluation of the adjustment result can be realized.
Step 140, carrying out quantization processing on the association relation, and determining a quantization relation among image information of a target image, the adjustment quality of a visual detection system and adjustment offset; the image information includes gray information and defect morphology.
In this step, the image information of the target image includes gray information and defect morphology.
Wherein, the defect morphology is represented by the pit morphology.
The quantization relation is used for representing the quantization relation among the image quality, the adjustment quality of the visual detection system and the adjustment offset of the visual system.
The adjustment quality of the visual detection system can be represented by the image quality of the target image, namely the gray information and defect morphology of the target image.
The higher the adjustment quality of the visual detection system is, the better the adjustment effect is, and the better the corresponding imaging effect is.
It can be understood that in the actual implementation process, the emphasis on the gray information and the defect morphology is different, which affects the determination of the imaging quality of the target image, and thus the determination of the adjustment quality.
In the step, quantitative indexes are designed to evaluate the adjustment quality by analyzing the change trends of the target background gray level, the target three-dimensional defect contrast, the morphology and the like of the target image when the adjustment offset gradually becomes larger.
By establishing the quantitative relation among the gray information, the defect form adjustment quality and the adjustment offset, the quantitative relation is convenient to correspondingly adjust based on the emphasis on the gray information and the defect form so as to more accurately judge the adjustment quality.
The inventor finds that in the research and development process, in the related technology, a method for acquiring a target image by setting the target and adjusting the setting angle of a camera based on the definition of the target image exists, but the method needs to judge the definition of the image subjectively by a detector, and then manually adjust the setting angle based on the definition until the detector considers that the definition meets the requirement. The large amount of manual operations and subjective judgment involved in the method affect the final debugging effect, and the consistency of the debugging is difficult to ensure when the device is installed and debugged for a large-scale series of visual detection system.
In the application, quantitative relation among the image quality, the adjustment quality of the visual detection system and the adjustment offset of the visual system is established, subjective judgment of detection personnel is not needed, the adjustment quality of the visual detection system obtained through the quantitative relation can be quantitatively and objectively evaluated, so that the influence of subjective judgment on the adjustment quality is avoided, the evaluation accuracy and precision are improved, and the adjustment consistency is effectively ensured; in addition, by establishing the quantization relation, repeated debugging process is avoided, and debugging steps are reduced, so that the debugging efficiency is improved.
In addition, the existing debugging flow is not required to be changed, and the target imaging is carried out on the pits of the target after the debugging is finished, so that the operation is simple and convenient.
According to the method for evaluating the quality of the assembly and adjustment of the visual inspection system, provided by the embodiment of the application, through establishing quantitative relation among the image quality, the quality of the assembly and adjustment of the visual inspection system and the assembly and adjustment deviation of the visual inspection system, the influence of subjective judgment on the quality of the assembly and adjustment is avoided, the accuracy and precision of evaluation are improved, the consistency of the appearance defect imaging of a single visual inspection system along with the change of time can be monitored, and the consistency of the appearance defect imaging among a plurality of visual inspection systems can be effectively improved; repeated debugging processes are avoided, and the debugging efficiency in the installation and debugging scene of a series of large-scale visual detection system equipment is remarkably improved.
The implementation of step 140 is described below by way of specific embodiments.
In some embodiments, step 140 may comprise:
performing image processing on target images in the target images, and determining the average gray level and pixel value standard deviation of the target images;
respectively determining a first dark pixel area and a second dark pixel area of image features corresponding to pits in a target image based on the average gray scale and the pixel value standard deviation;
Determining a target quantization relation corresponding to a target image based on the first dark pixel area, the second dark pixel area, the emphasis factor and the hardening and tempering amount;
the emphasis factor is used for representing the emphasis degree of gray information and defect morphology, and the target image is acquired by the visual detection system under the target tone offset in a plurality of different tone offsets.
In this embodiment, the target image of interest is a target image acquired at a target mount offset.
The target quantization relation is a quantization relation corresponding to the target tuning offset.
The emphasis factor is used for representing the emphasis degree of gray information and defect morphology, and can be customized based on actual conditions.
For example, in the case of paying more attention to the defect morphology, the emphasis ratio corresponding to the defect morphology may be appropriately increased; when the gradation of the image is emphasized, the emphasis ratio corresponding to the gradation information can be appropriately increased.
For example, the emphasis factor may be set to λ, which takes a value of 0-100.
In actual implementation, the average gray scale of the target image of interest can be determined by the following formula:
wherein, the liquid crystal display device comprises a liquid crystal display device,
the average gray scale of the target image of the target; x (i, j) is the pixel value of the pixel point at the (i, j) position; w is the width of the target image of interest; h is the height of the target image of interest.
The standard deviation of pixel values of the target image of interest can be determined by the following formula:
var is the standard deviation of pixel values of the target image; x (i, j) is the pixel value of the pixel point at the (i, j) position;
the average gray scale of the target image of the target; w is the width of the target image of interest; h is the height of the target image of interest.
After determining the average gray and pixel value standard deviation of the target image, the target quantization relation corresponding to the target image can be determined based on the average gray and pixel value standard deviation.
In some embodiments, determining the first dark pixel area and the second dark pixel area of the image feature corresponding to the pit in the target image, respectively, based on the average gray scale and the standard deviation of the pixel values, may include:
determining a first threshold based on a difference between the average gray scale and a standard deviation of pixel values of the target multiple;
determining a first dark pixel area based on a first threshold, a height of the target image of interest, and a width of the target image of interest;
determining a second threshold based on the sum of the average gray scale and the standard deviation of the pixel values of the target multiples;
a second dark pixel area is determined based on the second threshold, the height of the target image of interest, and the width of the target image of interest.
In this embodiment, the target multiple may be user-defined based, such as set to three or four times, etc., and the present application is not limited.
In the actual implementation process, taking the target multiple as a triple example, the standard deviation of the pixel value obtained by subtracting the average gray level from the triple is taken as a first threshold value, and the dark pixel area of the pit defect in the target image is calculated to be taken as the first dark pixel area;
and calculating the dark pixel area of the pit defect in the target image by adopting the standard deviation of the average gray level plus three times of pixel value as a second threshold value, and taking the dark pixel area as the second dark pixel area.
For example, the formula may be:
determining a first dark pixel area, wherein D is the first dark pixel area; x (i, j) is the pixel value of the pixel point at the (i, j) position;
the average gray scale of the target image of the target; var is the standard deviation of pixel values of the target image of interest.
The formula can be used:
determining a second dark pixel area, wherein L is the second dark pixel area; x (i, j) is the pixel value of the pixel point at the (i, j) position;
the average gray scale of the target image of the target; var is the standard deviation of pixel values of the target image of interest.
After the first dark pixel area and the second dark pixel area are obtained, a target quantization relation corresponding to the target image can be determined based on the first dark pixel area, the second dark pixel area, the emphasis factor and the hardening and tempering amount.
In some embodiments, determining the target quantization relation corresponding to the target image based on the first dark pixel area, the second dark pixel area, the emphasis factor, and the trim amount may include:
based on the formula:
determining a target quantitative relation corresponding to a target image, wherein Z is the target adjustment of a visual detection systemAdjusting quality under the offset; d is the first dark pixel area; l is the second dark pixel area; lambda is a emphasis factor;
is the average gray scale.
In this embodiment, λ has a value of 0-100, and is used to characterize the grayscale or defect morphology of the emphasis image.
For example, when λ is 50, the target images in which the adjustment offsets are 0mm,0.5mm,1mm, and 1.5mm as shown in fig. 6 are respectively subjected to adjustment quality evaluation, and the evaluation results are 88, 70, 51, and 27 in this order; as can be seen, as the tuning offset increases, the score of the tuning quality corresponding to the tuning offset gradually decreases, and the tuning effect deteriorates.
According to the method for evaluating the quality of the assembly and adjustment of the visual inspection system, provided by the embodiment of the application, the emphasis factors are set to establish the quantitative relation among the gray information, the defect form, the assembly and adjustment quality and the assembly and adjustment offset based on the emphasis factors, so that the emphasis factors are conveniently adjusted to correspondingly adjust the quantitative relation based on the emphasis degree of the gray information and the defect form, the assembly and adjustment quality can be accurately judged, and the method has higher use flexibility and wider application scene.
In some embodiments, after step 140, the method may further comprise:
determining the actual adjustment quality corresponding to the visual detection system to be detected based on the quantitative relation;
and adjusting the visual detection system to be detected based on the actual adjustment quality.
In this embodiment, the visual inspection system to be inspected is a visual inspection system that needs to perform adjustment offset inspection during the actual inspection process.
In the actual application process, the product to be detected and the target are placed on the same imaging surface for imaging, the actual adjustment offset of the visual detection system to be detected and the actual adjustment quality under the actual adjustment offset can be determined based on the target image of the target, the quantization relation and the target image under the ideal adjustment condition, and the actual adjustment quality of the current visual detection system to be detected is characterized to be poor in the condition that the actual adjustment quality and the target adjustment quality are large in difference, so that the visual detection system to be detected can be further adjusted based on the actual adjustment offset, and the adjustment quality is improved.
According to the method for evaluating the quality of the assembly and adjustment of the visual detection system, the actual quality of the assembly and adjustment of the visual detection system is determined through the quantitative relation, so that a user can monitor the imaging state of a single device conveniently, the difference between the defect presentation state and the initial state can be found timely, the user can be reminded to calibrate or re-assemble the device, and the real-time dynamic monitoring of the defect presentation state in the use process can be realized.
According to the method for evaluating the quality of the assembly quality of the visual detection system, which is provided by the embodiment of the application, the execution main body can be an assembly quality evaluation device of the visual detection system. In the embodiment of the present application, a method for evaluating the quality of the visual inspection system by using the quality evaluation device for the visual inspection system will be described as an example.
The embodiment of the application also provides a device for evaluating the quality of the assembly of the visual detection system.
As shown in fig. 8, the device for evaluating the quality of the assembly of the visual inspection system includes: a first processing module 810, a second processing module 820, a third processing module 830, and a fourth processing module 840.
The first processing module 810 is configured to adjust a system parameter of the visual detection system to a target parameter based on an imaging effect of a product image corresponding to a product to be detected acquired by the visual detection system, where the target parameter is used to enable the imaging effect to reach a target range;
the second processing module 820 is configured to respectively obtain, under the target parameter, a plurality of target images corresponding to the target collected by the visual detection system under a plurality of different adjustment offsets, where the product to be detected and the target are located on the same imaging plane, and a plurality of pits with different sizes are provided on the surface of the target;
The third processing module 830 is configured to extract an image feature corresponding to a pit in the target image, and determine an association relationship between the image feature and the adjustment offset;
a fourth processing module 840, configured to perform quantization processing on the association relationship, and determine a quantization relational expression between the image information of the target image, the tuning quality of the visual detection system, and the tuning offset; the image information includes gray information and defect morphology.
According to the visual inspection system installation and adjustment quantity evaluation device, through establishing quantitative relation among the image quality, the visual inspection system installation and adjustment quality and the visual inspection system installation and adjustment offset, the influence of subjective judgment on the installation and adjustment quality is avoided, the evaluation accuracy and precision are improved, the consistency of the appearance defect imaging of a single visual inspection system along with the change of time can be monitored, and the consistency of the appearance defect imaging among a plurality of visual inspection systems can be effectively improved; repeated debugging processes are avoided, and the debugging efficiency in the installation and debugging scene of a series of large-scale visual detection system equipment is remarkably improved.
In some embodiments, the fourth processing module 840 may also be configured to:
Performing image processing on target images in the target images, and determining the average gray level and pixel value standard deviation of the target images;
respectively determining a first dark pixel area and a second dark pixel area of image features corresponding to pits in a target image based on the average gray scale and the pixel value standard deviation;
determining a target quantization relation corresponding to a target image based on the first dark pixel area, the second dark pixel area, the emphasis factor and the hardening and tempering amount;
the emphasis factor is used for representing the emphasis degree of gray information and defect morphology, and the target image is acquired by the visual detection system under the target tone offset in a plurality of different tone offsets.
According to the visual inspection system installation and adjustment quality evaluation device, the weighting factors are set to establish the quantitative relation among the gray information, the defect form, the installation and adjustment quality and the installation and adjustment offset based on the weighting factors, so that the weighting factors are conveniently adjusted to correspondingly adjust the quantitative relation based on the weighting degree of the gray information and the defect form, the installation and adjustment quality can be accurately judged, and the visual inspection system installation and adjustment quality evaluation device has high use flexibility and wide application scene.
In some embodiments, the fourth processing module 840 may also be configured to:
based on the formula:
determining a target quantization relation corresponding to a target image, wherein Z is the adjustment quality of the visual detection system under the target adjustment offset; d is the first dark pixel area; l is the second dark pixel area; lambda is a emphasis factor;
is the average gray scale.
In some embodiments, the fourth processing module 840 may also be configured to:
determining a first threshold based on a difference between the average gray scale and a standard deviation of pixel values of the target multiple;
determining a first dark pixel area based on a first threshold, a height of the target image of interest, and a width of the target image of interest;
determining a second threshold based on the sum of the average gray scale and the standard deviation of the pixel values of the target multiples;
a second dark pixel area is determined based on the second threshold, the height of the target image of interest, and the width of the target image of interest.
In some embodiments, the second processing module 820 may also be configured to:
acquiring a plurality of initial images corresponding to a target acquired by a visual detection system under a target adjustment offset in a plurality of different adjustment offsets;
preprocessing a plurality of initial images to obtain at least one target image acquired by a visual detection system under target adjustment;
A plurality of target images are acquired based on a plurality of different tone offsets.
In some embodiments, the apparatus may further comprise:
the fifth processing module is used for determining the actual adjustment quality corresponding to the visual detection system to be detected based on the quantization relation after performing quantization processing on the association relation and determining the image information of the target image, the adjustment quality of the visual detection system and the quantization relation between the adjustment offsets;
and the sixth processing module is used for adjusting the vision detection system to be detected based on the actual adjustment quality.
According to the visual inspection system installation and adjustment quality evaluation device provided by the embodiment of the application, the actual installation and adjustment quality of the visual inspection system is determined through the quantitative relation, so that a user can monitor the imaging state of a single device conveniently, discover the difference between the defect presentation state and the initial state in time, remind the user to calibrate or re-install the device, and realize the real-time dynamic monitoring of the defect presentation state in the use process.
The device for evaluating the quality of the visual inspection system in the embodiment of the present application may be an electronic device, or may be a component in an electronic device, such as an integrated circuit or a chip. The electronic device may be a terminal, or may be other devices than a terminal. By way of example, the electronic device may be a mobile phone, tablet computer, notebook computer, palm computer, vehicle-mounted electronic device, mobile internet appliance (Mobile Internet Device, MID), augmented reality (augmented reality, AR)/Virtual Reality (VR) device, robot, wearable device, ultra-mobile personal computer, UMPC, netbook or personal digital assistant (personal digital assistant, PDA), etc., but may also be a server, network attached storage (Network Attached Storage, NAS), personal computer (personal computer, PC), television (TV), teller machine or self-service machine, etc., and the embodiments of the present application are not limited in particular.
The device for evaluating the quality of the visual inspection system according to the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, which is not specifically limited in the embodiments of the present application.
The device for evaluating the quality of the visual inspection system according to the embodiment of the present application can implement each process implemented by the method embodiments of fig. 1 to 7, and in order to avoid repetition, a detailed description is omitted here.
In some embodiments, as shown in fig. 9, the embodiment of the present application further provides an electronic device 900, including a processor 901, a memory 902, and a computer program stored in the memory 902 and capable of running on the processor 901, where the program when executed by the processor 901 implements each process of the embodiment of the method for evaluating the quality of the package quality of the visual inspection system, and the process can achieve the same technical effect, and is not repeated herein.
The electronic device in the embodiment of the application includes the mobile electronic device and the non-mobile electronic device described above.
The embodiment of the present application further provides a non-transitory computer readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements each process of the embodiment of the method for evaluating the quality of the package of the visual inspection system, and can achieve the same technical effect, so that repetition is avoided, and details are not repeated here.
Wherein the processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes computer readable storage medium such as computer readable memory ROM, random access memory RAM, magnetic or optical disk, etc.
The embodiment of the application also provides a computer program product, which comprises a computer program, wherein the computer program realizes the method for evaluating the quality of the assembly quality of the visual inspection system when being executed by a processor.
Wherein the processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes computer readable storage medium such as computer readable memory ROM, random access memory RAM, magnetic or optical disk, etc.
The embodiment of the application further provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled with the processor, the processor is used for running a program or an instruction, implementing each process of the embodiment of the method for evaluating the quality of the assembly and the control of the visual inspection system, and achieving the same technical effect, so as to avoid repetition, and no further description is provided here.
It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, chip systems, or system-on-chip chips, etc.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solutions of the present application may be embodied essentially or in a part contributing to the prior art in the form of a computer software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing a terminal (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the methods described in the embodiments of the present application.
The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those of ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are also within the protection of the present application.
In the description of the present specification, reference to the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the application, the scope of which is defined by the claims and their equivalents.
Claims (10)
1. A method for evaluating the quality of the assembly of a visual inspection system is characterized by comprising the following steps:
adjusting system parameters of the visual detection system to target parameters based on imaging effects of product images corresponding to products to be detected, which are acquired by the visual detection system, wherein the target parameters are used for enabling the imaging effects to reach a target range;
under the target parameters, respectively acquiring a plurality of target images corresponding to a target acquired by the visual detection system under a plurality of different adjustment offsets, wherein the product to be detected and the target are positioned on the same imaging surface, and a plurality of pits with different sizes are arranged on the surface of the target;
extracting image features corresponding to the pits in the target image, and determining an association relationship between the image features and the adjustment offset;
carrying out quantization processing on the association relation, and determining a quantization relation among image information of the target image, the tuning quality of the visual detection system and the tuning offset; the image information includes gray information and defect morphology.
2. The method for evaluating the quality of adjustment of a visual inspection system according to claim 1, wherein the performing quantization processing on the association relation to determine a quantization relation among image information of the target image, the quality of adjustment of the visual inspection system, and the adjustment offset comprises:
Performing image processing on target images in the target images, and determining the average gray scale and pixel value standard deviation of the target images;
based on the average gray scale and the pixel value standard deviation, respectively determining a first dark pixel area and a second dark pixel area of an image feature corresponding to the pit in the target image;
determining a target quantization relation corresponding to the target image based on the first dark pixel area, the second dark pixel area, the emphasis factor and the adjustment quality;
the emphasis factor is used for representing the gray information and the emphasis degree of the defect morphology, and the target image is a target image acquired by the visual detection system under a target tone offset in the plurality of different tone offsets.
3. The method of claim 2, wherein determining the target quantization relation corresponding to the target image based on the first dark pixel area, the second dark pixel area, the emphasis factor, and the adjustment quality comprises:
based on the formula:
determining a target quantization relation corresponding to the target image, wherein Z is the adjustment quality of the visual detection system under the target adjustment offset; d is the first dark pixel area; l is the second dark pixel area; lambda is the emphasis factor; 
Is the average gray scale.
4. The method for evaluating the quality of an image according to claim 2, wherein determining the first dark pixel area and the second dark pixel area of the image feature corresponding to the pit in the target image based on the average gray scale and the standard deviation of the pixel values, respectively, comprises:
determining a first threshold based on a difference between the average gray scale and the standard deviation of the pixel values of the target multiple;
determining the first dark pixel area based on the first threshold, a height of the target image of interest, and a width of the target image of interest;
determining a second threshold based on a sum of the average gray scale and the standard deviation of the pixel values of the target multiples;
the second dark pixel area is determined based on the second threshold, the height of the target image of interest, and the width of the target image of interest.
5. The method for evaluating the quality of a visual inspection system according to any one of claims 1 to 4, wherein the respectively acquiring a plurality of target images corresponding to a target object acquired by the visual inspection system at a plurality of different tone offsets includes:
acquiring a plurality of initial images corresponding to the target acquired by the visual detection system under a target tone offset in the plurality of different tone offsets;
Preprocessing the plurality of initial images to obtain at least one target image acquired by a visual detection system under the target adjustment;
the plurality of target images are acquired based on the plurality of different tone offsets.
6. The method according to any one of claims 1 to 4, wherein after the quantization processing is performed on the association relation to determine the quantization relational expression among the image information of the target image, the adjustment quality of the visual inspection system, and the adjustment offset, the method further comprises:
based on the quantization relation, determining the actual adjustment quality corresponding to the visual detection system to be detected;
and adjusting the vision detection system to be detected based on the actual adjustment quality.
7. An apparatus for evaluating an adjustment amount of a visual inspection system, comprising:
the first processing module is used for adjusting system parameters of the visual detection system to target parameters based on the imaging effect of the product image corresponding to the product to be detected, which is acquired by the visual detection system, wherein the target parameters are used for enabling the imaging effect to reach a target range;
the second processing module is used for respectively acquiring a plurality of target images corresponding to a target, acquired by the visual detection system under a plurality of different adjustment offsets, of the target under the target parameters, wherein the product to be detected and the target are positioned on the same imaging surface, and a plurality of pits with different sizes are arranged on the surface of the target;
The third processing module is used for extracting image features corresponding to the pits in the target image and determining the association relationship between the image features and the adjustment offset;
the fourth processing module is used for carrying out quantization processing on the association relation and determining an image information of the target image, the adjustment quality of the visual detection system and a quantization relation between the adjustment offsets; the image information includes gray information and defect morphology.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for evaluating the quality of a package of a visual inspection system according to any one of claims 1 to 6 when the program is executed by the processor.
9. A non-transitory computer-readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method of evaluating the quality of fit of a visual inspection system according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements a method for evaluating the quality of a packaging of a visual inspection system according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211708942.6A CN116258674A (en) | 2022-12-29 | 2022-12-29 | Method and device for evaluating quality of assembly of visual inspection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211708942.6A CN116258674A (en) | 2022-12-29 | 2022-12-29 | Method and device for evaluating quality of assembly of visual inspection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116258674A true CN116258674A (en) | 2023-06-13 |
Family
ID=86687095
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211708942.6A Pending CN116258674A (en) | 2022-12-29 | 2022-12-29 | Method and device for evaluating quality of assembly of visual inspection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116258674A (en) |
-
2022
- 2022-12-29 CN CN202211708942.6A patent/CN116258674A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110225336B (en) | Method and device for evaluating image acquisition precision, electronic equipment and readable medium | |
| CN107918216B (en) | Image Mura defect evaluation method and system and readable storage medium | |
| CN112153371B (en) | Image quality detection method, device, storage medium and product detection method | |
| Watson | 31.1: Invited paper: The spatial standard observer: A human vision model for display inspection | |
| CN109655234B (en) | Automatic testing method for camera | |
| CN109949725B (en) | Image gray level standardization method and system for AOI system | |
| WO2017202114A1 (en) | Method and apparatus for determining illumination intensity for inspection, and optical inspection method and apparatus | |
| CN113065538A (en) | Pressure sensor detection method, device and equipment based on image recognition | |
| CN101207834A (en) | Method for checking digital camera articulation | |
| KR20060052414A (en) | Method and apparatus for detecting flat panel display by vision model | |
| CN106204523A (en) | A kind of image quality evaluation method and device | |
| CN110136212B (en) | DeMura equipment pixel point brightness extraction precision judging method and noise detection method | |
| CN116258674A (en) | Method and device for evaluating quality of assembly of visual inspection system | |
| CN112465780B (en) | Method and device for monitoring abnormal film thickness of insulating layer | |
| CN116297478A (en) | Method, device and system for detecting coating defects of photovoltaic glass | |
| CN116067671A (en) | Method, system and medium for testing vehicle paint quality | |
| CN115546131A (en) | Quantitative evaluation method for black ash on surface of strip steel and related equipment | |
| US10852250B1 (en) | Quantitative test method for striae in optical materials | |
| CN113008524B (en) | Screen light leakage detection method and device | |
| US7747066B2 (en) | Z-axis optical detection of mechanical feature height | |
| CN106713907A (en) | Display HDR image display performance evaluation method and device | |
| CN101354357A (en) | Method for analyzing micro-density image of tree annual ring | |
| JP2021148720A (en) | Inspection system, learning device, learning program, learning method, inspection device, inspection program, and inspection method | |
| KR100416775B1 (en) | Method to Measure a Brightness of an Display Device | |
| CN113724201B (en) | Image sensor correction effect quantitative evaluation method based on two-dimensional Fourier transform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |